FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2805981489> ?p ?o ?g. }

• W2805981489 abstract "In recent years, deep neural network models have shown to outperform many state of the art algorithms. The reason for this is, unsupervised pretraining with multi-layered deep neural networks have shown to learn better features, which further improves many supervised tasks. These models not only automate the feature extraction process but also provide with robust features for various machine learning tasks. But the unsupervised pretraining and feature extraction using multi-layered networks are restricted only to the input features and not to the output. The performance of many supervised learning algorithms (or models) depends on how well the output dependencies are handled by these algorithms [Dembczy´nski et al., 2012]. Adapting the standard neural networks to handle these output dependencies for any specific type of problem has been an active area of research [Zhang and Zhou, 2006, Ribeiro et al., 2012]. On the other hand, inference into multimodal data is considered as a difficult problem in machine learning and recently ‘deep multimodal neural networks’ have shown significant results [Ngiam et al., 2011, Srivastava and Salakhutdinov, 2012]. Several problems like classification with complete or missing modality data, generating the missing modality etc., are shown to perform very well with these models. In this work, we consider three nontrivial supervised learning tasks (i) multi-class classification (MCC), (ii) multi-label classification (MLC) and (iii) label ranking (LR), mentioned in the order of increasing complexity of the output. While multi-class classification deals with predicting one class for every instance, multi-label classification deals with predicting more than one classes for every instance and label ranking deals with assigning a rank to each label for every instance. All the work in this field is associated around formulating new error functions that can force network to identify the output dependencies. Aim of our work is to adapt neural network to implicitly handle the feature extraction (dependencies) for output in the network structure, removing the need of hand crafted error functions. We show that the multimodal deep architectures can be adapted for these type of problems (or data) by considering labels as one of the modalities. This also brings unsupervised pretraining to the output along with the input. We show that these models can not only outperform standard deep neural networks, but also outperform standard adaptations of neural networks for individual domains under various metrics over several data sets considered by us. We can observe that the performance of our models over other models improves even more as the complexity of the output/ problem increases." @default.
• W2805981489 created "2018-06-13" @default.
• W2805981489 creator A5049776939 @default.
• W2805981489 date "2015-01-01" @default.
• W2805981489 modified "2023-09-27" @default.
• W2805981489 title "Multimodal Deep Learning for Multi-Label Classification and Ranking Problems" @default.
• W2805981489 hasPublicationYear "2015" @default.
• W2805981489 type Work @default.
• W2805981489 sameAs 2805981489 @default.
• W2805981489 citedByCount "0" @default.
• W2805981489 crossrefType "dissertation" @default.
• W2805981489 hasAuthorship W2805981489A5049776939 @default.
• W2805981489 hasConcept C108583219 @default.
• W2805981489 hasConcept C119857082 @default.
• W2805981489 hasConcept C138885662 @default.
• W2805981489 hasConcept C154945302 @default.
• W2805981489 hasConcept C189430467 @default.
• W2805981489 hasConcept C2776214188 @default.
• W2805981489 hasConcept C2776401178 @default.
• W2805981489 hasConcept C2777212361 @default.
• W2805981489 hasConcept C41008148 @default.
• W2805981489 hasConcept C41895202 @default.
• W2805981489 hasConcept C50644808 @default.
• W2805981489 hasConcept C8038995 @default.
• W2805981489 hasConceptScore W2805981489C108583219 @default.
• W2805981489 hasConceptScore W2805981489C119857082 @default.
• W2805981489 hasConceptScore W2805981489C138885662 @default.
• W2805981489 hasConceptScore W2805981489C154945302 @default.
• W2805981489 hasConceptScore W2805981489C189430467 @default.
• W2805981489 hasConceptScore W2805981489C2776214188 @default.
• W2805981489 hasConceptScore W2805981489C2776401178 @default.
• W2805981489 hasConceptScore W2805981489C2777212361 @default.
• W2805981489 hasConceptScore W2805981489C41008148 @default.
• W2805981489 hasConceptScore W2805981489C41895202 @default.
• W2805981489 hasConceptScore W2805981489C50644808 @default.
• W2805981489 hasConceptScore W2805981489C8038995 @default.
• W2805981489 hasLocation W28059814891 @default.
• W2805981489 hasOpenAccess W2805981489 @default.
• W2805981489 hasPrimaryLocation W28059814891 @default.
• W2805981489 hasRelatedWork W2000469266 @default.
• W2805981489 hasRelatedWork W2017637319 @default.
• W2805981489 hasRelatedWork W2241525425 @default.
• W2805981489 hasRelatedWork W2518162332 @default.
• W2805981489 hasRelatedWork W2562194522 @default.
• W2805981489 hasRelatedWork W2599207826 @default.
• W2805981489 hasRelatedWork W2746222821 @default.
• W2805981489 hasRelatedWork W2783819585 @default.
• W2805981489 hasRelatedWork W2786485441 @default.
• W2805981489 hasRelatedWork W2806278221 @default.
• W2805981489 hasRelatedWork W2907269905 @default.
• W2805981489 hasRelatedWork W2941045407 @default.
• W2805981489 hasRelatedWork W2951829787 @default.
• W2805981489 hasRelatedWork W2963306618 @default.
• W2805981489 hasRelatedWork W2981802957 @default.
• W2805981489 hasRelatedWork W2986864381 @default.
• W2805981489 hasRelatedWork W3007188588 @default.
• W2805981489 hasRelatedWork W3011174949 @default.
• W2805981489 hasRelatedWork W3082029927 @default.
• W2805981489 hasRelatedWork W3103320289 @default.
• W2805981489 isParatext "false" @default.
• W2805981489 isRetracted "false" @default.
• W2805981489 magId "2805981489" @default.
• W2805981489 workType "dissertation" @default.